update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5975
-- Accuracy: 0.8653
-- F1: 0.8599
-- Precision: 0.8682
-- Recall: 0.8653
+- Loss: 0.6217
+- Accuracy: 0.8601
+- F1: 0.8587
+- Precision: 0.8603
+- Recall: 0.8601
 
 ## Model description
 
@@ -48,17 +48,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 6
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.1373        | 1.0   | 626  | 0.3654          | 0.8394   | 0.8434 | 0.8542    | 0.8394 |
-| 0.0674        | 2.0   | 1252 | 0.5459          | 0.8497   | 0.8499 | 0.8571    | 0.8497 |
-| 0.033         | 3.0   | 1878 | 0.5613          | 0.8394   | 0.8390 | 0.8435    | 0.8394 |
-| 0.0005        | 4.0   | 2504 | 0.5975          | 0.8653   | 0.8599 | 0.8682    | 0.8653 |
+| 0.1753        | 1.0   | 626  | 0.3718          | 0.8290   | 0.8323 | 0.8513    | 0.8290 |
+| 0.1849        | 2.0   | 1252 | 0.4400          | 0.8342   | 0.8309 | 0.8292    | 0.8342 |
+| 0.0853        | 3.0   | 1878 | 0.5032          | 0.8135   | 0.8171 | 0.8278    | 0.8135 |
+| 0.0046        | 4.0   | 2504 | 0.5403          | 0.8601   | 0.8615 | 0.8655    | 0.8601 |
+| 0.0002        | 5.0   | 3130 | 0.5898          | 0.8601   | 0.8587 | 0.8603    | 0.8601 |
+| 0.0002        | 6.0   | 3756 | 0.6217          | 0.8601   | 0.8587 | 0.8603    | 0.8601 |
 
 
 ### Framework versions